{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/liputan6-a-large-scale-indonesian-dataset-for","title":"Liputan6: A Large-scale Indonesian Dataset for Text Summarization","arxiv_id":"2011.00679","date":"2020-11-02","proceeding":"Asian Chapter of the Association for Computational Linguistics 2020","authors":["Fajri Koto","Jey Han Lau","Timothy Baldwin"],"abstract":"In this paper, we introduce a large-scale Indonesian summarization dataset. We harvest articles from Liputan6.com, an online news portal, and obtain 215,827 document-summary pairs. We leverage pre-trained language models to develop benchmark extractive and abstractive summarization methods over the dataset with multilingual and monolingual BERT-based models. We include a thorough error analysis by examining machine-generated summaries that have low ROUGE scores, and expose both issues with ROUGE it-self, as well as with extractive and abstractive summarization models.","url_abs":"https://arxiv.org/abs/2011.00679v1","url_pdf":"https://arxiv.org/pdf/2011.00679v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"liputan6-a-large-scale-indonesian-dataset-for","repo_url":"https://github.com/fajri91/sum_liputan6","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":null}],"tasks":[{"task_slug":"abstractive-text-summarization","task_name":"Abstractive Text Summarization"},{"task_slug":"articles","task_name":"Articles"},{"task_slug":"text-summarization","task_name":"Text Summarization"}],"methods":[],"datasets_introduced":[{"slug":"liputan6","name":"Liputan6","full_name":""}],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2011.00679","atlas_url":"https://app.syntology.ai/?focus=2011.00679","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}